team-communications
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill and its included Python scripts function as intended for project management tasks. Analysis of the source code and instructions confirms that there are no attempts to exfiltrate data, hardcode credentials, or execute unauthorized commands.
- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by ingesting and processing external data files (JSON and Markdown). Ingestion points: Data is loaded from user-specified files in scripts/meeting_load_auditor.py, scripts/channel_router.py, and scripts/status_update_scorer.py. Boundary markers: There are no explicit delimiters or instructions to ignore potential commands within the data. Capability inventory: The skill is limited to local text analysis and lacks network or subprocess capabilities. Sanitization: The scripts use standard parsing techniques without specific filtering for prompt injection patterns.
Audit Metadata